Contextual Entity Analysis for Content Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content delivery systems face inefficiencies in processing content requests, leading to poor user experience due to prolonged processing times, as they rely on complex computations that may not effectively identify relevant content items for end-users based on contextual entities.
Innovation Solution
A system and method that identifies contextual entities within electronic content, determining relevant content items by combining viewer attributes with attributes of the content being viewed, and transmitting these items dynamically over a network to enhance relevance and interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex computations are used to identify relevant content items, then content relevance to viewers is improved, but processing time increases
Solution Approach 1:
The system performs preliminary actions by pre-processing content items to extract and store contextual entities, attributes, and metadata in advance. When a viewer requests content, the system queries pre-processed data structures rather than performing complex computations on raw content, significantly reducing processing time while maintaining relevance accuracy.
Solution Approach 2:
The system segments content items into discrete contextual entities (people, places, things, events) with separate attribute structures. This segmentation allows the system to query specific entity attributes independently rather than processing entire content items, reducing computational complexity while preserving relevance identification capability.
2Measurement precision
If complex computations are performed for each content request, then content relevance is improved, but system productivity decreases
Solution Approach 1:
Content items are pre-processed offline to extract contextual entities, build attribute structures, and organize data in query-optimized formats. This preliminary action shifts computational burden from online request processing to offline batch processing, increasing system productivity for incoming requests while maintaining relevance accuracy through pre-analyzed content metadata.
Solution Approach 2:
The system creates simplified copies of content items in the form of structured metadata records containing contextual entities and attributes. These copies serve as proxies for full content items during query processing, enabling fast relevance determination without analyzing complete content, thus improving processing throughput.
3Device complexity
If traditional content delivery methods are used, then system simplicity is maintained, but user experience deteriorates due to poor content relevance
Solution Approach 1:
The system introduces contextual entity extraction and attribute-based matching as intermediary processes between content storage and content delivery. These intermediaries analyze content metadata and viewer context to bridge the gap between simple system structure and sophisticated content relevance requirements, improving user experience without fundamentally complicating the core delivery architecture.
Solution Approach 2:
The system changes the parameters used for content matching from traditional keyword-based approaches to contextual entity attributes (people, places, things, events). This parameter transformation enables more accurate relevance determination while maintaining system simplicity by operating on structured metadata rather than complex content analysis during delivery.
Data Source
AI summary
Techniques for responding to content requests that originate from remote computing devices are provided. In one technique, a content request that includes a viewer identifier of a user that requested web content and a contextual entity identifier of an entity that is referenced in the web content is received. In response to receiving the content request, based on the viewer identifier, first profile data about a viewer associated with the viewer identifier is retrieved. Also, based on the contextual entity identifier, second profile data about the entity is retrieved. Based on the first profile data and the second profile data, a content delivery campaign is identified. Particular content to deliver is determined based on the content delivery campaign. The particular content is sent to a computing device that initiated the content request.